AI RESEARCH
RoomPilot: Controllable Indoor Scene Synthesis via Multimodal Semantic Parsing
arXiv CS.CV
•
ArXi:2512.11234v2 Announce Type: replace Generating controllable indoor scenes is fundamental to applications in game development, architectural visualization, and embodied AI. However, existing approaches either a limited input modalities or rely on implicit generation processes that hinder precise control over scene structure and semantics. To address these limitations, we